Felipe Bravo-Marquez

Meta-level sentiment models for big social data analysis

People react to events, topics and entities by expressing their personal opinions and emotions. These reactions can correspond to a wide range of intensities, from very mild to strong. An adequate processing and understanding of these expressions has been the subject of research in several fields, such as business and politics. In this context, Twitter sentiment analysis, which is the task of automatically identifying and extracting subjective information from tweets, has received increasing attention from the Web mining community. Twitter provides an extremely valuable insight into human opinions, as well as new challenging Big Data problems. These problems include the processing of massive volumes of streaming data, as well as the automatic identification of human expressiveness within short text messages. In that area, several methods and lexical resources have been proposed in order to extract sentiment indicators from natural language texts at both syntactic and semantic levels. These approaches address different dimensions of opinions, such as subjectivity, polarity, intensity and emotion. This article is the first study of how these resources, which are focused on different sentiment scopes, complement each other. With this purpose we identify scenarios in which some of these resources are more useful than others. Furthermore, we propose a novel approach for sentiment classification based on meta-level features. This supervised approach boosts existing sentiment classification of subjectivity and polarity detection on Twitter. Our results show that the combination of meta-level features provides significant improvements in performance. However, we observe that there are important differences that rely on the type of lexical resource, the dataset used to build the model, and the learning strategy. Experimental results indicate that manually generated lexicons are focused on emotional words, being very useful for polarity prediction. On the other hand, lexicons generated with automatic methods include neutral words, introducing noise in the detection of subjectivity. Our findings indicate that polarity and subjectivity prediction are different dimensions of the same problem, but they need to be addressed using different subspace features. Lexicon-based approaches are recommendable for polarity, and stylistic part-of-speech based approaches are meaningful for subjectivity. With this research we offer a more global insight of the resource components for the complex task of classifying human emotion and opinion.

Combining strengths, emotions and polarities for boosting Twitter sentiment analysis

Twitter sentiment analysis or the task of automatically retrieving opinions from tweets has received an increasing interest from the web mining community. This is due to its importance in a wide range of fields such as business and politics. People express sentiments about specific topics or entities with different strengths and intensities, where these sentiments are strongly related to their personal feelings and emotions. A number of methods and lexical resources have been proposed to analyze sentiment from natural language texts, addressing different opinion dimensions. In this article, we propose an approach for boosting Twitter sentiment classification using different sentiment dimensions as meta-level features. We combine aspects such as opinion strength, emotion and polarity indicators, generated by existing sentiment analysis methods and resources. Our research shows that the combination of sentiment dimensions provides significant improvement in Twitter sentiment classification tasks such as polarity and subjectivity.

A novel deterministic approach for aspect-based opinion mining in tourism products reviews

This work proposes an extension of Bing Lius aspect-based opinion mining approach in order to apply it to the tourism domain. The extension concerns with the fact that users refer differently to different kinds of products when writing reviews on the Web. Since Lius approach is focused on physical product reviews, it could not be directly applied to the tourism domain, which presents features that are not considered by the model. Through a detailed study of on-line tourism product reviews, we found these features and then model them in our extension, proposing the use of new and more complex NLP-based rules for the tasks of subjective and sentiment classification at the aspect-level. We also entail the task of opinion visualization and summarization and propose new methods to help users digest the vast availability of opinions in an easy manner. Our work also included the development of a generic architecture for an aspect-based opinion mining tool, which we then used to create a prototype and analyze opinions from TripAdvisor in the context of the tourism industry in Los Lagos, a Chilean administrative region also known as the Lake District. Results prove that our extension is able to perform better than Lius model in the tourism domain, improving both Accuracy and Recall for the tasks of subjective and sentiment classification. Particularly, the approach is very effective in determining the sentiment orientation of opinions, achieving an F-measure of 92% for the task. However, on average, the algorithms were only capable of extracting 35% of the explicit aspect expressions, using a non-extended approach for this task. Finally, results also showed the effectiveness of our design when applied to solving the industrys specific issues in the Lake District, since almost 80% of the users that used our tool considered that our tool adds valuable information to their business.

Identifying Customer Preferences about Tourism Products Using an Aspect-based Opinion Mining Approach☆

Abstract In this study we extend Bing Lius aspect-based opinion mining technique to apply it to the tourism domain. Using this extension, we also offer an approach for considering a new alternative to discover consumer preferences about tourism products, particularly hotels and restaurants, using opinions available on the Web as reviews. An experiment is also conducted, using hotel and restaurant reviews obtained from TripAdvisor, to evaluate our proposals. Results showed that tourism product reviews available on web sites contain valuable information about customer preferences that can be extracted using an aspect-based opinion mining approach. The proposed approach proved to be very effective in determining the sentiment orientation of opinions, achieving a precision and recall of 90%. However, on average, the algorithms were only capable of extracting 35% of the explicit aspect expressions.

Building a Twitter opinion lexicon from automatically-annotated tweets

We propose a supervised model for expanding an opinion lexicon for Twitter.We combine automatically annotated tweets with existing hand-made opinion lexicons.We use POS tags and associations between words and sentiment as word-level features.Expanded words are mapped to a positive, negative, and neutral distribution.We outperform the performance obtained by using PMI semantic orientation alone. Opinion lexicons, which are lists of terms labeled by sentiment, are widely used resources to support automatic sentiment analysis of textual passages. However, existing resources of this type exhibit some limitations when applied to social media messages such as tweets (posts in Twitter), because they are unable to capture the diversity of informal expressions commonly found in this type of media.In this article, we present a method that combines information from automatically annotated tweets and existing hand-made opinion lexicons to expand an opinion lexicon in a supervised fashion. The expanded lexicon contains part-of-speech (POS) disambiguated entries with a probability distribution for positive, negative, and neutral polarity classes, similarly to SentiWordNet.To obtain this distribution using machine learning, we propose word-level attributes based on (a) the morphological information conveyed by POS tags and (b) associations between words and the sentiment expressed in the tweets that contain them. We consider tweets with both hard and soft sentiment labels. The sentiment associations are modeled in two different ways: using point-wise-mutual-information semantic orientation (PMI-SO), and using stochastic gradient descent semantic orientation (SGD-SO), which learns a linear relationship between words and sentiment. The training dataset is labeled by a seed lexicon formed by combining multiple hand-annotated lexicons.Our experimental results show that our method outperforms the three-dimensional word-level polarity classification performance obtained by using PMI-SO alone. This is significant because PMI-SO is a state-of-the-art measure for establishing world-level sentiment. Additionally, we show that lexicons created with our method achieve significant improvements over SentiWordNet for classifying tweets into polarity classes, and also outperform SentiStrength in the majority of the experiments.

Opinion Zoom: A Modular Tool to Explore Tourism Opinions on the Web

In this paper, we propose Opinion Zoom, a modular software that helps users in an easy manner to understand the vast amount of tourism opinions disposed all over the Web. We also successfully implemented and tested Opinion Zoom, encompassing the situation of the tourism industry in Los Lagos, also known as the Lake District, in Chile. Results showed the effectiveness of the designed proposal when applied to solving this specific industrys issues.

Emotion intensities in Tweets

This paper examines the task of detecting intensity of emotion from text. We create the first datasets of tweets annotated for anger, fear, joy, and sadness intensities. We use a technique called best--worst scaling (BWS) that improves annotation consistency and obtains reliable fine-grained scores. We show that emotion-word hashtags often impact emotion intensity, usually conveying a more intense emotion. Finally, we create a benchmark regression system and conduct experiments to determine: which features are useful for detecting emotion intensity, and, the extent to which two emotions are similar in terms of how they manifest in language.

Opinion Dynamics of Elections in Twitter

In this work we conduct an empirical study of opinion time series created from Twitter data regarding the 2008 U.S. elections. The focus of our proposal is to establish whether a time series is appropriate or not for generating a reliable predictive model. We analyze time series obtained from Twitter messages related to the 2008 U.S. elections using ARMA/ARIMA and GARCH models. The first models are used in order to assess the conditional mean of the process and the second ones to assess the conditional variance or volatility. The main argument we discuss is that opinion time series that exhibit volatility should not be used for long-term forecasting purposes. We present an in-depth analysis of the statistical properties of these time series. Our experiments show that these time series are not fit for predicting future opinion trends. Due to the fact that researchers have not provided enough evidence to support the alleged predictive power of opinion time series, we discuss how more rigorous validation of predictive models generated from time series could benefit the opinion mining field.

DOCODE 3.0 (DOcument COpy DEtector)

Extracting knowledge from document and Web pages for plagiarism detection.An information fusion based system for plagiarism detection in the educational institutions.Text mining algorithms for detecting plagiarism patterns in digital documents. Plagiarism refers to the act of presenting external words, thoughts, or ideas as ones own, without providing references to the sources from which they were taken. The exponential growth of different digital document sources available on the Web has facilitated the spread of this practice, making the accurate detection of it a crucial task for educational institutions. In this article, we present DOCODE 3.0, a Web system for educational institutions that performs automatic analysis of large quantities of digital documents in relation to their degree of originality. Since plagiarism is a complex problem, frequently tackled at different levels, our system applies algorithms in order to perform an information fusion process from multi data source to all these levels. These algorithms have been successfully tested in the scientific community in solving tasks like the identification of plagiarized passages and the retrieval of source candidates from the Web, among other multi data sources as digital libraries, and have proven to be very effective. We integrate these algorithms into a multi-tier, robust and scalable JEE architecture, allowing many different types of clients with different requirements to consume our services. For users, DOCODE produces a number of visualizations and reports from the different outputs to let teachers and professors gain insights on the originality of the documents they review, allowing them to discover, understand and handle possible plagiarism cases and making it easier and much faster to analyze a vast number of documents. Our experience here is so far focused on the Chilean situation and the Spanish language, offering solutions to Chilean educational institutions in any of their preferred Virtual Learning Environments. However, DOCODE can easily be adapted to increase language coverage.

Hypergeometric language model and zipf-like scoring function for web document similarity retrieval

The retrieval of similar documents in the Web from a given document is different in many aspects from information retrieval based on queries generated by regular search engine users. In this work, a new method is proposed for Web similarity document retrieval based on generative language models and meta search engines. Probabilistic language models are used as a random query generator for the given document. Queries are submitted to a customizable set of Web search engines. Once all results obtained are gathered, its evaluation is determined by a proposed scoring function based on the Zipf law. Results obtained showed that the proposed methodology for query generation and scoring procedure solves the problem with acceptable levels of precision.